I build at the point where product, AI, code, and visual storytelling meet.
AI Product Builder & Creative Technologist
I turn rough ideas into mobile products, AI systems, generative video, and things that leave the screen as physical objects.
Across layers
ACROSS LAYERS
Across layers
My advantage is not one tool. It is the ability to connect product logic, UX, AI, code, media, infrastructure, and physical making into one execution loop.
- IDEA
- PRODUCT LOGIC
- UX / UI
- AI WORKFLOW
- CODE
- MEDIA
- INFRASTRUCTURE
- DEPLOYMENT
- ITERATION
CAPABILITIES
Evidence, not percentages
Product systems, not isolated screens
- Feature architecture
- Onboarding thinking
- Monetization boundaries
- Release readiness
- Iterative feedback
Mobile products from interaction to backend
- Expo / React Native
- TypeScript
- Navigation
- OTA updates
- Supabase
- Widgets
AI as product infrastructure
- Claude
- Gemini
- Structured outputs
- Fallback logic
- Server-side proxy
- Vision & voice
Generative media with production discipline
- Veo / Kling
- Storyboards
- Continuity
- Shot design
- Remotion
- AI music workflows
Small systems that remove manual work
- Supabase Edge Functions
- Cloudflare Workers
- Webhooks
- Telegram bots
I care about the path to production
- GitHub
- Coolify
- Hetzner
- Cloudflare
- Push-to-deploy
From pixels to physical objects
- Blender
- Cinema 4D
- 3ds Max
- FDM printing
- Bambu Studio
- Physical iteration
MY OPERATING SYSTEM
My operating system
Fast does not have to mean careless. I use AI agents aggressively, not blindly — I keep the work grounded in project context, real constraints, review, and deployment.
- 01
Find the real problem
I reduce a vague idea to one useful user action and one clear outcome.
- 02
Build the system, not only the screen
I map data, states, edge cases, AI behavior, backend boundaries, and the path to deployment.
- 03
Use agents aggressively, not blindly
Claude Code, Codex, and specialized AI workflows accelerate execution. Project memory, constraints, review, and verification keep the work coherent.
- 04
Iterate in public reality
Real devices, real API limits, weird edge cases, store requirements, broken generations, and failed prints are part of the process.
- 05
Ship, observe, refine
Push, deploy, test, collect feedback, fix what matters, repeat.
AGENT-NATIVE, PRODUCT-LED
Agent-native, product-led
I use AI coding agents as a development environment, not a one-shot code generator. I keep project memory, split work into stages, review behavior, and push changes through a real Git and deployment workflow.
ABOUT
About
I'm Serhii — a builder based in Kyiv. I move between AI products, mobile apps, video, automation, and 3D, depending on where the problem takes me.
Most of what I know, I picked up by actually building things: figuring out the UX, wiring up Supabase, turning a camera into an AI-powered workflow, or taking a model from Blender to a real, physical print.
What ties it all together is pretty simple — I like taking a messy idea and turning it into something that actually works.
CONTACT
Have a hard idea? Good.
This is where I do my best work: product, AI, creative technology, fast execution.